cabinwandClaude Opus 5
c0c1558464
Round 3 tested one hypothesis from round 2's data: levels the agent rated 3 carried 59% more 反差 than the rest, so select for it. With both rounds now at ~100 runs, the answer is in and it is no. The back band went from 2.39 ± 0.10 to 2.19 ± 0.08, roughly two standard errors apart, and the levels averaging 2.5 or better fell from 11 to 6. Contrast is real and it does correlate with being rated harder; selecting on it does not produce harder levels. The low retest reliability does not rescue the change either — r = 0.55 limits ranking one level against another, not the mean of eighteen levels measured a hundred times. So round 2's levels are the ones handed over, rebuilt from its runs via round-set --emitCampaign. select-50 cannot reproduce them: the pool it drew from has been rebuilt since, so the same flags now return different levels. The runs are the record. Rule bot on the shipped set: 50/50 cleared, dead taps 0.00, blind rotations 0.12, worst blind streak 1. 198 tests pass. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
65 lines
3.7 KiB
JavaScript
65 lines
3.7 KiB
JavaScript
#!/usr/bin/env node
|
||
// Rebuild the level set a bench round actually played, from the round's runs.
|
||
//
|
||
// node scripts/round-set.mjs --round=R2 [--out=…]
|
||
//
|
||
// Disk snapshots of "the set round N played" are not trustworthy: select-50
|
||
// writes levels/campaign-50.json in place, so any selection experiment run
|
||
// between the round and the copy silently replaces it. One such copy kept only
|
||
// 28 of the 50 boards its round had played, which would have made the round
|
||
// comparison compare a set against somebody else's levels.
|
||
//
|
||
// Runs store the whole board and its campaign index, so the round is its own
|
||
// record. That record cannot drift.
|
||
import { readdirSync, readFileSync, writeFileSync } from 'node:fs';
|
||
import { resolve } from 'node:path';
|
||
import { deepLevelKey } from '../src/deep-lock.js';
|
||
|
||
const args = Object.fromEntries(process.argv.slice(2).map(a => { const [k, ...v] = a.replace(/^--/, '').split('='); return [k, v.length ? v.join('=') : true]; }));
|
||
const ROUND = String(args.round ?? 'R2');
|
||
|
||
export function roundSet(round, dir = resolve('bench/runs')) {
|
||
const byBoard = new Map();
|
||
for (const f of readdirSync(dir)) {
|
||
if (!f.endsWith('.json') || f === 'index.json') continue;
|
||
try {
|
||
const d = JSON.parse(readFileSync(resolve(dir, f), 'utf8'));
|
||
if (d.status === 'playing' || !d.level?.tiles) continue;
|
||
if (!new RegExp(`^${round} · `).test(String(d.agent))) continue;
|
||
const k = deepLevelKey(d.level);
|
||
if (!byBoard.has(k)) byBoard.set(k, { level: d.level, runs: [] });
|
||
byBoard.get(k).runs.push(d);
|
||
} catch { /* torn read */ }
|
||
}
|
||
return [...byBoard.values()].sort((a, b) => (a.level.campaign?.index ?? 0) - (b.level.campaign?.index ?? 0));
|
||
}
|
||
|
||
// Ship a round that was already played. Re-running select-50 cannot reproduce
|
||
// one: the pool it drew from has since been rebuilt, so the same flags now
|
||
// return different levels. The runs are the only exact record.
|
||
function emitCampaign(levels) {
|
||
writeFileSync(resolve('levels/campaign-50.json'),
|
||
JSON.stringify({ generated: `round-set ${ROUND}`, version: 1, count: levels.length, levels }, null, 1));
|
||
const chapterSize = 10;
|
||
const chapters = Array.from({ length: Math.ceil(levels.length / chapterSize) },
|
||
(_, i) => ['起步', '转起来', '看清路', '深一点', '收束'][i] ?? `第 ${i + 1} 章`);
|
||
writeFileSync(resolve('src/levels-c50.js'),
|
||
`// Generated by scripts/round-set.mjs --round=${ROUND} --emitCampaign — do not edit by hand.\n`
|
||
+ `export const C50_CAMPAIGN = ${JSON.stringify({ id: 'c50', name: '五十关调优版', description: `按演出、反差与旋转深度选出的 50 关，难度递增。`, chapters, chapterSize }, null, 1)};\n`
|
||
+ `export const C50_LEVELS = ${JSON.stringify(levels)};\n`);
|
||
console.log('已写入 levels/campaign-50.json 与 src/levels-c50.js');
|
||
}
|
||
|
||
if (import.meta.url === `file://${process.argv[1]}`) {
|
||
const rows = roundSet(ROUND);
|
||
const levels = rows.map(r => r.level);
|
||
console.log(`${ROUND}：${levels.length} 关，共 ${rows.reduce((s, r) => s + r.runs.length, 0)} 局`);
|
||
console.log(`旋转深度 ${JSON.stringify(levels.reduce((m, l) => (m[l.campaign?.rotations ?? '?'] = (m[l.campaign?.rotations ?? '?'] || 0) + 1, m), {}))}`);
|
||
console.log(`家族 ${JSON.stringify(levels.reduce((m, l) => (m[l.campaign?.family ?? '?'] = (m[l.campaign?.family ?? '?'] || 0) + 1, m), {}))}`);
|
||
if (args.out) { writeFileSync(resolve(args.out), JSON.stringify({ generated: `round-set ${ROUND}`, count: levels.length, levels }, null, 1)); console.log(`已写入 ${args.out}`); }
|
||
if (args.emitCampaign) {
|
||
if (levels.length !== 50) { console.error(`只反建出 ${levels.length} 关，不足 50，拒绝写入`); process.exit(1); }
|
||
emitCampaign(levels);
|
||
}
|
||
}
|